Sandbox
1,578 repos for ai · Any agentClear
tangosdev/
sm64ds-decomp

From-scratch, byte-matching decompilation of Super Mario 64 DS (sm64ds decomp) into C, with a live progress atlas and matching tools.

155
Xopoko/
build-swift-apps

Build, debug, profile, test, refactor, and release Swift apps across iOS, macOS, Xcode, SwiftUI, SwiftPM, Tuist, and App Store Connect.

45
DenisSergeevitch/
game-sensitivity-coach

An agent skill for evidence-based mouse sensitivity tuning, cross-game conversion, and gameplay review. Works with Codex, Claude Code, and Agent Skills hosts.

34
buildswithpaul/
Frappe_Assistant_Core

Infrastructure that connects LLMs to ERPNext. Frappe Assistant Core works with the Model Context Protocol (MCP) to expose ERPNext functionality to any compatible Language Model

307
Zhen-Bo/
smell-check

Agent Skill for code and test smell audits. Evidence-ranked findings from Refactoring, Clean Code, and the test-smell literature. Formerly pragmatic-code-review.

237
arjun988/
blender-skills

94 specialist Blender skills for Cursor, Claude Code, Kiro & Codex -> MCP-powered production pipeline from blockout to engine export.

182

HTTP-native chat and notes for agents whose sandbox only allows webfetch — every write is a plain GET. Runs technocore.chat.

149

Instant, accurate Unreal Engine API lookups instead of expensive source file reads, saving your agent tokens, context, and hallucinations.

95
lc198707/
anti-lie

Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effectiveness on LiarBench v0.2.

89
Cognitohazard/
ltspice-mcp

MCP server giving LLMs the ability to design, simulate, and analyze SPICE circuits via LTSpice and NGspice

41
limingrui679-design/
high-stakes-analytics-decision-lab

A platform-neutral analytical Skill that profiles messy data, selects case-adaptive methods, and produces source-backed visual reports for high-stakes decisions.

576
Superior-Trade/
superior-skills

Open agent skills and tool schemas for Superior Trade — build, backtest, and deploy trading strategies on Hyperliquid

209
AaronZ345/
codebase-argus

Multi-agent codebase review for PRs, CI, and downstream fork syncs.

58
sandraschi/
calibremcp

Calibre library automation via FastMCP — metadata, shelves, RAG-friendly export. Companion to Calibre, not a replacement. For Cursor / Claude Desktop.

42
Emily2040/
nano-banana-image-skill

Production-grade, agent-portable image prompting skill for Nano Banana Pro and Nano Banana 2 in the Gemini image family

30

📻Free and open-sourced terminal/ssh/sftp/ftp/telnet/serialport/RDP/VNC/Spice client(Linux, Mac, Windows, Android, HarmonyOS, iOS)

15k
sosoj92/
jarvis-assistant-vocal

Assistant vocal local en francais : Claude ou Ollama (offline), domotique Hue, OBS, agenda, navigateur, appels Twilio, serveur MCP. Python.

250

Battle-tested agent skills mapping the footguns of Kotlin, Compose Multiplatform and the desktop JVM — mined from a production music app, not from documentation.

217
samihalawa/
visual-ui-debug-agent-mcp

Visual UI testing and debugging MCP server with Playwright, screenshots, DOM inspection, workflow validation, and visual diffs.

81
xxxbrian/
mcp-rquest

A MCP server providing realistic browser-like HTTP request capabilities with accurate TLS/JA3/JA4 fingerprints for bypassing anti-bot measures. It also supports converting PDF and HTML documents to Markdown for easier processing by LLMs.

48

Record any browser page as GIF or video via MCP — powered by Playwright + ffmpeg

47

Artifact layer for agent-human representations. One API call, one SVG. Zero dependencies, renders in any markdown.

41

Enterprise Governance Layer (Identity, RBAC, Credentials, Auditing, Logging, Tracing) for the Model Context Protocol SDK

39